Standard

Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection. / Мамаев, Иван Дмитриевич; Митрофанова, Ольга Александровна.

Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022). Springer Nature, 2024. p. 85-97 (Springer Geography; Vol. Part F2317).

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Harvard

Мамаев, ИД & Митрофанова, ОА 2024, Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection. in Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022). Springer Geography, vol. Part F2317, Springer Nature, pp. 85-97, International Conference "Internet and Modern Society" (IMS-2022), Санкт-Петербург, Russian Federation, 23/06/22. https://doi.org/10.1007/978-3-031-50609-3_7

APA

Мамаев, И. Д., & Митрофанова, О. А. (2024). Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection. In Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022) (pp. 85-97). (Springer Geography; Vol. Part F2317). Springer Nature. https://doi.org/10.1007/978-3-031-50609-3_7

Vancouver

Мамаев ИД, Митрофанова ОА. Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection. In Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022). Springer Nature. 2024. p. 85-97. (Springer Geography). https://doi.org/10.1007/978-3-031-50609-3_7

Author

Мамаев, Иван Дмитриевич ; Митрофанова, Ольга Александровна. / Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection. Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022). Springer Nature, 2024. pp. 85-97 (Springer Geography).

BibTeX

@inproceedings{1030626f551f4aa19e0dfd3e9d820043,
title = "Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection",
abstract = "Today, social networks are among the main means of organizing interactions between people, and their analysis is a burning issue. One of the central tasks of social network analysis is the task of detecting hidden communities that is based on the study of user interactions. The procedures of their detection are based on three main approaches: cluster analysis, graph methods, and hybrid techniques. Recently, a new group of methods, namely, topic modeling, has begun to evolve and it allows taking into account semantic and associative links among the analyzed texts. In this paper, we conduct a series of comparative experiments with probabilistic and contextualized topic models in order to determine the most stable one. The experiments are performed on the corpus of 2020–2021 Russian LiveJournal posts which contains more than 12,500 texts. The results show that contextualized BERT models form the most stable connections between the texts that can become a sound basis for creating a model of hidden communities of Russian LiveJournal users.",
keywords = "Topic modeling, Corpus linguistics, Computational semantics, LDA, ATM, ATM, BERT, Computational semantics, Corpus linguistics, LDA, Topic modeling",
author = "Мамаев, {Иван Дмитриевич} and Митрофанова, {Ольга Александровна}",
year = "2024",
month = feb,
day = "21",
doi = "10.1007/978-3-031-50609-3_7",
language = "English",
isbn = "978-3-031-50608-6",
series = "Springer Geography",
publisher = "Springer Nature",
pages = "85--97",
booktitle = "Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022)",
address = "Germany",
note = "International Conference {"}Internet and Modern Society{"} (IMS-2022) : International Workshop «Computational Linguistics» (CompLing-2022), IMS-2022 (CompLing-2022) ; Conference date: 23-06-2022 Through 24-06-2022",
url = "http://ims.ifmo.ru/ru/pages/2/programma.htm, http://ims.ifmo.ru/ru",

}

RIS

TY - GEN

T1 - Adaptation of Static and Contextualized Topic Modeling Techniques to Hidden Community Detection

AU - Мамаев, Иван Дмитриевич

AU - Митрофанова, Ольга Александровна

N1 - Conference code: XXIV

PY - 2024/2/21

Y1 - 2024/2/21

N2 - Today, social networks are among the main means of organizing interactions between people, and their analysis is a burning issue. One of the central tasks of social network analysis is the task of detecting hidden communities that is based on the study of user interactions. The procedures of their detection are based on three main approaches: cluster analysis, graph methods, and hybrid techniques. Recently, a new group of methods, namely, topic modeling, has begun to evolve and it allows taking into account semantic and associative links among the analyzed texts. In this paper, we conduct a series of comparative experiments with probabilistic and contextualized topic models in order to determine the most stable one. The experiments are performed on the corpus of 2020–2021 Russian LiveJournal posts which contains more than 12,500 texts. The results show that contextualized BERT models form the most stable connections between the texts that can become a sound basis for creating a model of hidden communities of Russian LiveJournal users.

AB - Today, social networks are among the main means of organizing interactions between people, and their analysis is a burning issue. One of the central tasks of social network analysis is the task of detecting hidden communities that is based on the study of user interactions. The procedures of their detection are based on three main approaches: cluster analysis, graph methods, and hybrid techniques. Recently, a new group of methods, namely, topic modeling, has begun to evolve and it allows taking into account semantic and associative links among the analyzed texts. In this paper, we conduct a series of comparative experiments with probabilistic and contextualized topic models in order to determine the most stable one. The experiments are performed on the corpus of 2020–2021 Russian LiveJournal posts which contains more than 12,500 texts. The results show that contextualized BERT models form the most stable connections between the texts that can become a sound basis for creating a model of hidden communities of Russian LiveJournal users.

KW - Topic modeling

KW - Corpus linguistics

KW - Computational semantics

KW - LDA

KW - ATM

KW - ATM

KW - BERT

KW - Computational semantics

KW - Corpus linguistics

KW - LDA

KW - Topic modeling

UR - https://www.mendeley.com/catalogue/01d37869-576e-3943-8463-db994eb5f740/

U2 - 10.1007/978-3-031-50609-3_7

DO - 10.1007/978-3-031-50609-3_7

M3 - Conference contribution

SN - 978-3-031-50608-6

T3 - Springer Geography

SP - 85

EP - 97

BT - Digital Geography. Proceedings of the International Conference on Internet and Modern Society (IMS 2022)

PB - Springer Nature

T2 - International Conference "Internet and Modern Society" (IMS-2022)

Y2 - 23 June 2022 through 24 June 2022

ER -

ID: 117017397